Text Recognition Using Segmented Language Databases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing text recognition techniques consume excessive resources and degrade memory efficiency due to the use of a combined database for all languages, leading to slow text recognition and inefficient resource utilization.
Innovation Solution
A method and terminal for recognizing text by generating tag information when switching between languages, using separate databases for each language, and recognizing text based on generated tag information and screen images, allowing for efficient resource management and improved recognition speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a combined database storing characteristics of all kinds of languages is used to recognize text, then text recognition can handle multiple languages, but text recognition time increases and memory efficiency degrades
Solution Approach 1:
The patent divides the combined database into multiple separate language-specific databases. Each database stores characteristics for a specific language, allowing the system to select and use only the relevant database for the current text input language. This segmentation reduces the amount of data that needs to be processed during text recognition, thereby decreasing recognition time while maintaining multi-language capability.
Solution Approach 2:
The patent performs preliminary classification to identify the language of the text input before initiating the text recognition process. By determining the language type in advance, the system can pre-select the appropriate language-specific database, avoiding the need to search through or process data from all language databases. This preliminary action optimizes resource utilization and reduces recognition time.
2Adaptability or versatility
If a combined database storing characteristics of all kinds of languages is used to recognize text, then text recognition can handle multiple languages, but memory efficiency degrades
Solution Approach 1:
The patent segments the large combined database into multiple smaller, language-specific databases. Each database contains only the characteristics necessary for recognizing one language. This segmentation reduces the amount of memory required to store and process text recognition data at any given time, as the system loads and uses only the relevant language database rather than the entire combined database, thereby improving memory efficiency.
Solution Approach 2:
The patent extracts and separates language-specific characteristics from the combined database, creating independent language databases. This extraction allows the system to eliminate unnecessary data from the processing workflow by selecting only the relevant language database for the current input, reducing memory resource consumption while maintaining the ability to handle multiple languages.
Data Source
AI summary
Provided is a method of recognizing text in a terminal, the method including generating first tag information about a kind of language set in a user interface (UI) for inputting text and a location of a cursor at a time point when a text input has started, when the UI for inputting text displayed on the terminal is executed; when a language switch request that requests the terminal to switch the kind of language set in the UI is received, generating second tag information about a kind of switched language and a location of the cursor at a time point of receiving the language switch request; when the text input is finished, storing a screen image of the terminal; and recognizing the text input to the terminal based on at least one piece of tag information and the screen image.